DOCSLIB.ORG

A Survey on Recent Named Entity Recognition and Relationship Extraction Techniques on Clinical Texts

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
A Survey on Recent Named Entity Recognition and Relationship Extraction Techniques on Clinical Texts applied sciences Review A Survey on Recent Named Entity Recognition and Relationship Extraction Techniques on Clinical Texts Priyankar Bose 1,* , Sriram Srinivasan 2,3, William C. Sleeman IV 1,2,3, Jatinder Palta 2,3, Rishabh Kapoor 2,3 and Preetam Ghosh 1,2 1 Department of Computer Science, Virginia Commonwealth University, Richmond, VA 23284, USA; [email protected] (W.C.S.IV); [email protected] (P.G.) 2 Department of Radiation Oncology, Virginia Commonwealth University, Richmond, VA 23284, USA; [email protected] (S.S.); [email protected] (J.P.); [email protected] (R.K.) 3 National Radiation Oncology Program, Department of Veteran Affairs, Richmond, VA 23249, USA * Correspondence: [email protected] Abstract: Significant growth in Electronic Health Records (EHR) over the last decade has provided an abundance of clinical text that is mostly unstructured and untapped. This huge amount of clinical text data has motivated the development of new information extraction and text mining techniques. Named Entity Recognition (NER) and Relationship Extraction (RE) are key components of information extraction tasks in the clinical domain. In this paper, we highlight the present status of clinical NER and RE techniques in detail by discussing the existing proposed NLP models for the two tasks and their performances and discuss the current challenges. Our comprehensive survey on Citation: Bose, P.; Srinivasan, S.; clinical NER and RE encompass current challenges, state-of-the-art practices, and future directions in Sleeman, W.C., IV; Palta, J.; Kapoor, information extraction from clinical text. This is the first attempt to discuss both of these interrelated R.; Ghosh, P. A Survey on Recent topics together in the clinical context. We identified many research articles published based on Named Entity Recognition and Relationship Extraction Techniques different approaches and looked at applications of these tasks. We also discuss the evaluation metrics on Clinical Texts. Appl. Sci. 2021, 11, that are used in the literature to measure the effectiveness of the two these NLP methods and future 8319. https://doi.org/10.3390/ research directions. app11188319 Keywords: electronic health records; clinical text; natural language processing; named entity Academic Editors: Arturo recognition; relationship extraction; machine learning Montejo-Ráez and Salud María Jiménez-Zafra Received: 7 August 2021 1. Introduction Accepted: 2 September 2021 The amount of text generated every day is increasing drastically in different domains Published: 8 September 2021 such as health care, news articles, scientific literature, and social media. Since 2010, the In- ternational Data Corporation (IDC) has predicted that the amount of data can potentially Publisher’s Note: MDPI stays neutral grow 50-fold to 40 billion terabytes by 2020 [1]. Textual data is very common in most with regard to jurisdictional claims in domains, but automated comprehension is difficult due to its unstructured nature and has published maps and institutional affil- iations. led to the design of several text mining (TM) techniques in the last decade. TM refers to the extraction of interesting and nontrivial patterns or knowledge from text [2]. Common text mining tasks include text preprocessing, text classification, question- answering, clustering, and statistical techniques. TM has become extremely popular and useful in the biomedical and healthcare Copyright: © 2021 by the authors. domains. In healthcare, about 80% of the total medical data is unstructured and untapped Licensee MDPI, Basel, Switzerland. after its creation [3]. This unstructured data from hospitals, healthcare clinics, or biomedical This article is an open access article labs can come in many forms such as text, images, and signals. Out of the various text distributed under the terms and conditions of the Creative Commons mining tasks and techniques, our goal in this paper is to review the current state-of-the- Attribution (CC BY) license (https:// art in Clinical Named Entity Recognition (NER) and Relationship Extraction (RE)-based creativecommons.org/licenses/by/ techniques. Clinical NER is a natural language processing (NLP) method used for extracting 4.0/). important medical concepts and events i.e., clinical NEs from the data [4]. Relationship Appl. Sci. 2021, 11, 8319. https://doi.org/10.3390/app11188319 https://www.mdpi.com/journal/applsci Appl. Sci. 2021, 11, 8319 2 of 30 Extraction (RE) is used for detecting and classifying the annotated semantic relationships between the recognized entities. Significant research on NER and RE has been carried out in the past both on clinical narratives and other types of text. For example, in the sentence, “Her white count remained elevated despite discontinuing her G-CSF”, the words in bold are the various entities in the sentence. After the entities are recognized, the relationship between two or more entities is extracted. In this case, “her white count” and “elevated” are found to be related to each other in a manner dissimilar to the nature of the relationship between “elevated” and “her G-CSF”. In the sentence “Atorvastatin is found to have therapeutic effects in breast cancer although no clinical trials are performed at present”, the NE of interest includes the name of the drug (atorvastatin) and the disease name (breast cancer), whereas the drug–disease relation (atorvastatin–breast cancer) is the relationship of interest. Figure1 shows a pictorial representation of the association between NER and RE. Figure 1. Association between Named Entity Recognition and Relationship Extraction. 2. Background Over the years, many toolkits and applications have been introduced to address different NLP tasks in the clinical domain, including NER and RE. The WEKA Data Mining Software [5] first came into existence in the late nineties. It was updated several times over the years to include NLP systems for language identification, tokenization, sentence boundary detection, and named entity recognition. Later on, the clinical NLP toolkit, CLAMP (Clinical Language Annotation, Modeling, and Processing) [6] was introduced in 2018 and provides a GUI-based state-of-the-art NLP system. CLAMP achieved good performance on NER and concept encoding and is also publicly available for research use. Comprehend Medical, a NER- and RE-related Web Service (2019) [7], is a very recent effort that introduces an NLP service launched under Amazon Web Services (AWS). Likewise, other research works have also addressed these topics, which motivates this review. A high- level overview of machine learning, neural networks, and evaluation metrics is presented below before we review clinical NER- and RE-related tasks. 2.1. Machine Learning Machine learning (ML) is a type of data-driven Artificial Intelligence (AI) that pro- vides the ability to learn about a system without explicit programming. ML algorithms are applied in many scientific domains and the most common applications include recommen- dation systems, data mining, and pattern recognition. ML is classified into one of the four subdomains: • Supervised Learning: With these algorithms, the training data are given ground- truth labels, which can be used for learning the underlying patterns in the dataset. Appl. Sci. 2021, 11, 8319 3 of 30 Classification and regression algorithms are most commonly used, including Naive Bayes [8], Support Vector Machines (SVM) [9], and Decision Trees [10]. • Unsupervised Learning: In this case, the training dataset is not given labels and, thus, many of the solutions attempt to find patterns without any prior guidance. Commonly used algorithms in this category are association rules and clustering methods, such as K-Means [11] or DBSCAN [12]. • Semi-Supervised Learning: Here, only some of the training data is labeled, putting these solutions in a space somewhere between fully supervised and unsupervised learning. Text classification [13] is one of the most common applications for semi- supervised learning. • Reinforcement Learning: Using a reward system, a reinforcement learning agent optimizes future returns based on prior results. This iterative, continuous learning process mirrors how humans learn from their experiences when interacting with an environment. Deep Adversarial Networks [14] and Q-Learning [15] are well known reinforcement learning algorithms. 2.2. Neural Networks The traditional machine learning algorithms often perform well with structured data but can struggle with unstructured or semi-structured data, i.e., human information processing mechanisms such as vision and speech [16]. Neural networks, specifically deep learning algorithms, have shown promising results with NLP and image analysis tasks. In neural networks, the input is processed through different layers of the network, where each layer transforms the features of the dataset following some mathematical function. The concept of neural networks follows the mechanism that the human brain uses to solve a problem. Once the data is processed through different layers within a neural network, the output layer performs the classification. In general, this approach does not require as much human intervention as the nested layers using different hierarchies try to find the hidden patterns on their own. 2.3. Common Evaluation Metrics The F1-score is a popular evaluation metric for the two NLP functions reviewed in this paper. Comparisons can be classified as exact or relaxed match [17]. Relaxed match only considers the correct type and
Load more

Recommended publications
  • Information Extraction Based on Named Entity for Tourism Corpus
    Information Extraction based on Named Entity for Tourism Corpus Chantana Chantrapornchai Aphisit Tunsakul Dept. of Computer Engineering Dept. of Computer Engineering Faculty of Engineering Faculty of Engineering Kasetsart University Kasetsart University Bangkok, Thailand Bangkok, Thailand [email protected] [email protected] Abstract— Tourism information is scattered around nowa- The ontology is extracted based on HTML web structure, days. To search for the information, it is usually time consuming and the corpus is based on WordNet. For these approaches, to browse through the results from search engine, select and the time consuming process is the annotation which is to view the details of each accommodation. In this paper, we present a methodology to extract particular information from annotate the type of name entity. In this paper, we target at full text returned from the search engine to facilitate the users. the tourism domain, and aim to extract particular information Then, the users can specifically look to the desired relevant helping for ontology data acquisition. information. The approach can be used for the same task in We present the framework for the given named entity ex- other domains. The main steps are 1) building training data traction. Starting from the web information scraping process, and 2) building recognition model. First, the tourism data is gathered and the vocabularies are built. The raw corpus is used the data are selected based on the HTML tag for corpus to train for creating vocabulary embedding. Also, it is used building. The data is used for model creation for automatic for creating annotated data.
    [Show full text]
  • Extraction of Semantic Relations from Bioscience Text
    Extraction of semantic relations from bioscience text by Barbara Rosario GRAD. (University of Trieste, Italy) 1995 A dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy in Information Management and Systems and the Designated Emphasis in Communication, Computation and Statistics in the GRADUATE DIVISION of the UNIVERSITY OF CALIFORNIA, BERKELEY Committee in charge: Professor Marti Hearst, Chair Professor John C. I. Chuang Professor Dan Klein Fall 2005 The dissertation of Barbara Rosario is approved: Professor Marti Hearst, Chair Date Professor John C. I. Chuang Date Professor Dan Klein Date University of California, Berkeley Fall 2005 Extraction of semantic relations from bioscience text Copyright c 2005 by Barbara Rosario Abstract Extraction of semantic relations from bioscience text by Barbara Rosario Doctor of Philosophy in Information Management and Systems and the Designated Emphasis in Communication, Computation and Statistics University of California, Berkeley Professor Marti Hearst, Chair A crucial area of Natural Language Processing is semantic analysis, the study of the meaning of linguistic utterances. This thesis proposes algorithms that ex- tract semantics from bioscience text using statistical machine learning techniques. In particular this thesis is concerned with the identification of concepts of interest (“en- tities”, “roles”) and the identification of the relationships that hold between them. This thesis describes three projects along these lines. First, I tackle the problem of classifying the semantic relations between nouns in noun compounds, to characterize, for example, the “treatment-for-disease” rela- tionship between the words of migraine treatment versus the “method-of-treatment” relationship between the words of sumatriptan treatment.
    [Show full text]
  • A Methodology for Engineering Domain Ontology Using Entity Relationship Model
    (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 10, No. 8, 2019 A Methodology for Engineering Domain Ontology using Entity Relationship Model Muhammad Ahsan Raza1, M. Rahmah2, Sehrish Raza3, A. Noraziah4, Roslina Abd. Hamid5 Faculty of Computer Systems and Software Engineering, Universiti Malaysia Pahang, Kuantan, Malaysia1, 2, 4, 5 Institute of Computer Science and Information Technology, The Women University, Multan, Pakistan3 Abstract—Ontology engineering is an important aspect of The proposed procedure of ontology engineering (OE) is semantic web vision to attain the meaningful representation of novel in two aspects: (1) it is based on well know ER-schema data. Although various techniques exist for the creation of which is readily available for most of the database-based ontology, most of the methods involve the number of complex organizations or can be developed efficiently for any domain of phases, scenario-dependent ontology development, and poor interest with accuracy. (2) The method proposes instant and validation of ontology. This research work presents a lightweight cost-effective rules for ER to ontology translation while approach to build domain ontology using Entity Relationship maintaining all semantic checks. The ER-schema and (ER) model. Firstly, a detailed analysis of intended domain is translation model (viewing the two facets as simple and performed to develop the ER model. In the next phase, ER to portable) support the development of ontology for any ontology (EROnt) conversion rules are outlined, and finally the knowledge domain. Focusing on the discipline of information system prototype is developed to construct the ontology. The proposed approach investigates the domain of information technology where the learning material related to the technology curriculum for the successful interpretation of curriculum is highly unstructured, we have developed an OE concepts, attributes, relationships of concepts and constraints tool that captures semantics from the ER-schema and among the concepts of the ontology.
    [Show full text]
  • Generating Knowledge Graphs by Employing Natural Language Processing and Machine Learning Techniques Within the Scholarly Domain
    Generating Knowledge Graphs by Employing Natural Language Processing and Machine Learning Techniques within the Scholarly Domain Danilo Dess`ıa,b,c,∗, Francesco Osborned, Diego Reforgiato Recuperoa, Davide Buscaldie, Enrico Mottad aDepartment of Mathematics and Computer Science, University of Cagliari, Cagliari, Italy bFIZ Karlsruhe - Leibniz Institute for Information Infrastructure, Germany cKarlsruhe Institute of Technology, Institute AIFB, Germany dKnowledge Media Institute, The Open University, Milton Keynes, UK eLIPN, CNRS (UMR 7030), University Paris 13, Villetaneuse, France Abstract The continuous growth of scientific literature brings innovations and, at the same time, raises new challenges. One of them is related to the fact that its analysis has become difficult due to the high volume of published papers for which manual effort for an- notations and management is required. Novel technological infrastructures are needed to help researchers, research policy makers, and companies to time-efficiently browse, analyse, and forecast scientific research. Knowledge graphs i.e., large networks of en- tities and relationships, have proved to be effective solution in this space. Scientific knowledge graphs focus on the scholarly domain and typically contain metadata de- scribing research publications such as authors, venues, organizations, research topics, and citations. However, the current generation of knowledge graphs lacks of an explicit representation of the knowledge presented in the research papers. As such, in this pa- per, we present a
    [Show full text]
  • Clinical Relationships Extraction Techniques from Patient Narratives
    IJCSI International Journal of Computer Science Issues, Vol.10, Issue 1, January 2013 www.IJCSI.org Clinical Relationships Extraction Techniques from Patient Narratives Wafaa Tawfik Abdel-moneim1, Mohamed Hashem Abdel-Aziz2, and Mohamed Monier Hassan3 1Information System Department, Faculty of Computers and Informatics, Zagazig University Banha, Egypt 2Information System Department, Faculty of Computers and Informatics, Ain-Shames University Cairo, Egypt 3Information System Department, Faculty of Computers and Informatics, Zagazig University Zagazig, Egypt Abstract Retrieval (IR), Natural Language Processing (NLP), The Clinical E-Science Framework (CLEF) project was used to Information Extraction (IE) and Data Mining (DM). NLP extract important information from medical texts by building a is commonly divided into several layers of processing: system for the purpose of clinical research, evidence-based lexical, syntactic, and semantic level. The lexical level healthcare and genotype-meets-phenotype informatics. The processing deals with words that can be recognized, system is divided into two parts, one part concerns with the analyzed, and identified to enable further processing. The identification of relationships between clinically important syntactic level analysis deals with identification of entities in the text. The full parses and domain-specific grammars structural relationships between groups of words in had been used to apply many approaches to extract the sentences, and the semantic level is concerned with the relationship. In the second part of the system, statistical machine content-oriented perspective or the meaning attributed to learning (ML) approaches are applied to extract relationship. A the various entities identified within the syntactic level [1]. corpus of oncology narratives that hand annotated with clinical Natural Language Processing (NLP) has been widely relationships can be used to train and test a system that has been applied in biomedicine, particularly to improve access to the ever-burgeoning research literature.
    [Show full text]
  • Supervised Learning for Relationship Extraction from Textual Documents
    Supervised Learning for Relationship Extraction From Textual Documents Joao˜ Pedro Lebre Magalhaes˜ Pereira Thesis to obtain the Master of Science Degree in Information Systems and Computer Engineering Examination Committee Chairperson : Prof. Jose´ Carlos Alves Pereira Monteiro Supervisor: Prof. Bruno Emanuel da Grac¸a Martins Co-Supervisor: Prof. Helena Isabel de Jesus Galhardas Member of the Committee: Prof. David Manuel Martins de Matos November 2013 Abstract nformation Extraction (IE) is the task of automatically extracting structured information from unstruc- Itured data, aiming to facilitate the use of said data by other applications. A typical sub-problem is the extraction of relationships from textual documents, which aims at identifying and classifying the rela- tionships expressed between entities mentioned in the texts. In order to extract relationships from a raw text, it is important to pre-process the data, organizing the textual contents into useful data structures, with techniques from Natural Language Processing. Furthermore, since relationships are expressed be- tween entities, it is mandatory to identify the entities using an entity extraction method, which is another sub-problem of IE. Assigning a relationship type to a pair of entities can be seen as a classification problem. Therefore, su- pervised machine learning techniques can be applied. In this thesis, we used Support Vector Machines (SVM), which we trained with basis on online methods similar to Pegasos [27]. Two specific modeling choices have been tested. The first one is a simple online solution that trains SVM models considering a single kernel. The second approach is based on the idea of online multiple kernel learning. With existing datasets and common pre-processing tools, we formulated a benchmark, which was then used to evaluate kernel-based methods.
    [Show full text]
  • Using Text to Build Semantic Networks for Pharmacogenomics ⇑ Adrien Coulet A,B, Nigam H
    Journal of Biomedical Informatics xxx (2010) xxx–xxx Contents lists available at ScienceDirect Journal of Biomedical Informatics journal homepage: www.elsevier.com/locate/yjbin Using text to build semantic networks for pharmacogenomics ⇑ Adrien Coulet a,b, Nigam H. Shah a, Yael Garten c, Mark Musen a, Russ B. Altman a,b,c,d, a Department of Medicine, 300 Pasteur Drive, Room S101, Mail Code 5110, Stanford University, Stanford, CA 94305, USA b Department of Genetics, Mail Stop-5120, Stanford University, Stanford, CA 94305, USA c Stanford Biomedical Informatics, 251 Campus Drive, MSOB, Room X215, Mail Code 5479, Stanford University, Stanford, CA 94305, USA d Department of Bioengineering, 318 Campus Drive, Room S172, Mail Code 5444, Stanford University, Stanford, CA 94305, USA article info abstract Article history: Most pharmacogenomics knowledge is contained in the text of published studies, and is thus not avail- Received 13 May 2010 able for automated computation. Natural Language Processing (NLP) techniques for extracting relation- Available online xxxx ships in specific domains often rely on hand-built rules and domain-specific ontologies to achieve good performance. In a new and evolving field such as pharmacogenomics (PGx), rules and ontologies Keywords: may not be available. Recent progress in syntactic NLP parsing in the context of a large corpus of phar- Relationship extraction macogenomics text provides new opportunities for automated relationship extraction. We describe an Pharmacogenomics ontology of PGx relationships built starting from a lexicon of key pharmacogenomic entities and a syn- Natural Language Processing tactic parse of more than 87 million sentences from 17 million MEDLINE abstracts. We used the syntactic Ontology Knowledge acquisition structure of PGx statements to systematically extract commonly occurring relationships and to map them Data integration to a common schema.
    [Show full text]
  • Automatic Classification and Relationship Extraction for Multi-Lingual and Multi-Granular Events from Wikipedia
    Automatic Classification and Relationship Extraction for Multi-Lingual and Multi-Granular Events from Wikipedia Daniel Hienert1, Dennis Wegener1 and Heiko Paulheim2 1 GESIS – Leibniz Institute for the Social Sciences Unter Sachsenhausen 6-8, 50667 Cologne, Germany {daniel.hienert, dennis.wegener}@gesis.org 2 Technische Universität Darmstadt Knowledge Engineering Group Hochschulstraße 10, 64283 Darmstadt, Germany [email protected] Abstract. Wikipedia is a rich data source for knowledge from all domains. As part of this knowledge, historical and daily events (news) are collected for different languages on special pages and in event portals. As only a small amount of events is available in structured form in DBpedia, we extract these events with a rule-based approach from Wikipedia pages. In this paper we focus on three aspects: (1) extending our prior method for extracting events for a daily granularity, (2) the automatic classification of events and (3) finding relationships between events. As a result, we have extracted a data set of about 170,000 events covering different languages and granularities. On the basis of one language set, we have automatically built categories for about 70% of the events of another language set. For nearly every event, we have been able to find related events. Keywords: Historical Events, News, Wikipedia, DBpedia 1 Introduction Wikipedia is an extensive resource for different types of events like historical events or news that are user-contributed and quality-proven. Although there is plenty of information on historical events in Wikipedia, only a small fraction of these events is available in a structured form in DBpedia.
    [Show full text]
  • A Semantic Relationship Mining Method Among Disorders, Genes
    Zhang et al. BMC Medical Informatics and Decision Making 2020, 20(Suppl 4):283 https://doi.org/10.1186/s12911-020-01274-z RESEARCH Open Access A semantic relationship mining method among disorders, genes, and drugs from different biomedical datasets Li Zhang1, Jiamei Hu1, Qianzhi Xu1, Fang Li2, Guozheng Rao3,4* and Cui Tao2* From The 4th International Workshop on Semantics-Powered Data Analytics Auckland, New Zealand. 27 October 2019 Abstract Background: Semantic web technology has been applied widely in the biomedical informatics field. Large numbers of biomedical datasets are available online in the resource description framework (RDF) format. Semantic relationship mining among genes, disorders, and drugs is widely used in, for example, precision medicine and drug repositioning. However, most of the existing studies focused on a single dataset. It is not easy to find the most current relationships among disorder-gene-drug relationships since the relationships are distributed in heterogeneous datasets. How to mine their semantic relationships from different biomedical datasets is an important issue. Methods: First, a variety of biomedical datasets were converted into RDF triple data; then, multisource biomedical datasets were integrated into a storage system using a data integration algorithm. Second, nine query patterns among genes, disorders, and drugs from different biomedical datasets were designed. Third, the gene-disorder- drug semantic relationship mining algorithm is presented. This algorithm can query the relationships among various entities from different datasets. Results and conclusions: We focused on mining the putative and the most current disorder-gene-drug relationships about Parkinson’s disease (PD). The results demonstrate that our method has significant advantages in mining and integrating multisource heterogeneous biomedical datasets.
    [Show full text]
  • Information Extraction
    R Foundations and Trends! in Databases Vol. 1, No. 3 (2007) 261–377 c 2008 S. Sarawagi ! DOI: 10.1561/1500000003 Information Extraction Sunita Sarawagi Indian Institute of Technology, CSE, Mumbai 400076, India, [email protected] Abstract The automatic extraction of information from unstructured sources has opened up new avenues for querying, organizing, and analyzing data by drawing upon the clean semantics of structured databases and the abundance of unstructured data. The field of information extraction has its genesis in the natural language processing community where the primary impetus came from competitions centered around the recog- nition of named entities like people names and organization from news articles. As society became more data oriented with easy online access to both structured and unstructured data, new applications of struc- ture extraction came around. Now, there is interest in converting our personal desktops to structured databases, the knowledge in scien- tific publications to structured records, and harnessing the Internet for structured fact finding queries. Consequently, there are many different communities of researchers bringing in techniques from machine learn- ing, databases, information retrieval, and computational linguistics for various aspects of the information extraction problem. This review is a survey of information extraction research of over two decades from these diverse communities. We create a taxonomy of the field along various dimensions derived from the nature of the extraction task, the techniques used for extraction, the variety of input resources exploited, and the type of output produced. We elaborate on rule-based and statistical methods for entity and relationship extrac- tion. In each case we highlight the different kinds of models for cap- turing the diversity of clues driving the recognition process and the algorithms for training and efficiently deploying the models.
    [Show full text]
  • Acquiring Evolving Semantic Relationships for Wordnet to Enhance Information Retrieval Ms.D.Akila1 Dr
    Ms.D.Akila et al. / International Journal of Engineering and Technology (IJET) Acquiring Evolving Semantic Relationships for WordNet to Enhance Information Retrieval Ms.D.Akila1 Dr. C.Jayakumar2 1Research Scholar, Bharathiar University, Coimbatore, Tamilnadu Asst.Professor, Dept. of computer Applications & IT, Guru Shree ShantiVijai Jain College for Women, Chennai, Tamilnadu Email:[email protected]: 09962278701 2Research Supervisor, Bharathiar University, Coimbatore, Tamilnadu Professor, Department of Computer Science and Engineering, R.M.K Engineering College, KavaraiPettai- 601206, Tamilnadu Email: [email protected] no: 09884217734 Abstract :Lexical Knowledge base such as WordNet has been used as a valuable tool for measuring semantic similarity in various Information Retrieval (IR) applications. It is a domain independent lexical database. Since, the quality of semantic relationship in WordNet has not upgraded appropriately for the current usage in the modern IR. Building the WordNet from scratch is not an easy task for keeping updated with current terminology and concepts. Therefore, this paper undergoes a different perspective that automatically updates an existing lexical ontology uses knowledge resources such as the Wikipedia and the Web search engine. This methodology has established the recently evolving relations and also aligns the existing relations between concepts based on its usage over time. It consists of three main phases such as candidate article generation, lexical relationship extraction and generalization and WordNet alignment. In candidate article generation, disambiguation mapping disambiguates ambiguous links between WordNet concepts and Wikipedia articles and returns a set of word-article pairings. Lexical relationship extraction phase includes two algorithms, Lexical Relationship Retrieval (LRR) algorithm discovers the set of lexical patterns exists between concepts and sequential pattern grouping algorithm generalizes lexical patterns and computes corresponding weights based on its frequencies.
    [Show full text]
  • Recognizing, Naming and Exploring Structure in RDF Data
    WEBSTYLEGUIDE INSTITUT FÜR SOFTWARE &SYSTEMS ENGINEERING Universitätsstraße 6a 86135 Augsburg Recognizing, Naming and Exploring Structure in RDF Data Linnea Passing Masterarbeit im Elitestudiengang Software Engineering REFERAT IIIA6 (INTERNET) Email [email protected] Servicetelefon 089 / 2180 – 9898 Mo./Di./Do./Fr. 09:00 Uhr bis 12:00 Uhr Di./Do. 14:00 Uhr bis 17:00 Uhr WEBSTYLEGUIDE INSTITUT FÜR SOFTWARE &SYSTEMS ENGINEERING Universitätsstraße 6a 86135 Augsburg Recognizing, Naming and Exploring Structure in RDF Data Matrikelnummer: 1227301 Beginn der Arbeit: 25. November 2013 Abgabe der Arbeit: 22. Mai 2014 Erstgutachter: Prof. Dr. Alfons Kemper, Technische Universität München Zweitgutachter: Prof. Dr. Alexander Knapp, Universität Augsburg Betreuer: Prof. Dr. Peter Boncz, Centrum Wiskunde & Informatica, Amsterdam Florian Funke, Technische Universität München Manuel Then, Technische Universität München REFERAT IIIA6 (INTERNET) Email [email protected] Servicetelefon 089 / 2180 – 9898 Mo./Di./Do./Fr. 09:00 Uhr bis 12:00 Uhr Di./Do. 14:00 Uhr bis 17:00 Uhr Erklärung Hiermit versichere ich, dass ich diese Masterarbeit selbständig verfasst habe. Ich habe dazu keine anderen als die angegebenen Quellen und Hilfsmittel verwendet. Garching, den 22. Mai 2014 Linnea Passing Abstract The Resource Description Framework (RDF) is the de facto standard for representing semantic data, employed e.g., in the Semantic Web or in data-intense domains such as the Life Sciences. Data in the RDF format can be handled efficiently using relational database systems (RDBMSs), because decades of research in RDBMSs led to mature techniques for storing and querying data. Previous work merely focused on the performance gain achieved by leveraging RDBMS techniques, but did not take other advantages, such as providing a SQL-based interface to the dataset and exposing relationships, into account.
    [Show full text]